0:00 Hello friends in this video I'm going to show you how to install comfy UI and get it running comfy UI is an extremely powerful user interface because you have total freedom total control to create your own workflows I'm going to give you some Advanced workflows you can work with I'm going to show you some Basics and I'm also going to set you up with an advanced extension that you're going to thank me for by the way do you know why chickens are so funny because AI this is comy UI and this is what we will be installing today this is also comy UI let's delve into this and go over the user interface together all the links are going to be in the description below and first of all we're going to go to
0:46 GitHub and find the comy UI so if you scroll down here you have installing or you can just scroll down even further then you have for Windows nowadays you don't need to get clones you can just direct link to download after you download that you're going to have a s zip file and you can use WinRAR or you can use 7even zip I personally prefer 7even zip then you can just either extract to wherever you want or you know just extract in the current location it's a rather big file so it will take you some time you're going to go into the folder and there's a read me here that says very important but it basically just says that if you have a Nvidia GPU you're going to use this P file but if you don't you're going to run by CPU which should also be
1:33 noticeably slower and there's also some troubleshooting here like if you get a red error in the UI make sure you have a model checkpoint so we're going to download that as well if you need to update your confy UI it says so in the read me here but you can also go you can go into the update here and just press update comy UI now if you are using automatic 111 or have another installation of stable Fusion where you already have models you can go into the confy UI directory here and rename this and just remove the example here then you should be able to edit this with notepad and then you can set your base path to where your automatic 1111 is now if you don't have that installed you can just skip that I do have it installed so I can just do like
2:21 this that will make sure after I save this that all my models that I'm using in automatic 111 will be used in confy UI as well now if you don't have that or any models at all I recommend that you download a model from civi so let's do that let's take deliberate here for example and we're just going to download that and then inside your models folder here so these are all the folders where you're going to be placing your various models now if you have no idea what this is just go into checkpoints and put your regular save tensors or ckpt files here I just dropped my deliberate model into here now you're all all set to start comy UI like we talked about previously
3:06 you're just going to run Nvidia GPU and after a few seconds you will have comy UI launched and this will be the default interface that you will see so these are nodes so similar to other user interfaces like automatic 1111 the features are the same but everything is connected by nodes and really the power of nodes is that you can then take take all the features and connect them together basically almost however you want and you can add multiple nodes and create your own workflows so here we have our load checkpoint or our load models node and here you can select the model that you want now I have a lot of models but if you just follow this
3:52 tutorial and don't have anything installed you should have the deliberate here for example which is the model that we downloaded from civi now we have a F prompt set here which is beautiful scenery nature glass ball landscape purple Galaxy ball we have a negative prompt here now you can't see this is a negative prompt because it just says clip text and code prompt uh this can be renamed so let's just type positive prompt here so you understand what it is what they're doing just rename this to negative prompt now you don't have to do this this is just Tri your sake and as you can see here the K sampler here we have connection going from the positive prompt here so you can see that this line here going to the positive and
4:38 this's is line from negative here going to negative so that is how the sampler understands what text is the positive prompt and what text is the negative prompt now you can switch these around you can detach these and let's say you want to change this this is the negative instead so I just drag this to negative and then you can connect this to the positive if you would want that so you can switch things up on the Fly let's put them back into positive and negative and as you can see the model here is going straight back to the bottle here so from the load checkpoint we're sending the model line to sampler and the vae here and you can't see that because it goes behind but if you can see that this red goes to this red down
5:25 here the VA code so if I were to render this or Q prompt that it says here it will start rendering similar to as it does in automatic 1111 and we would have an image coming into save image here and we can uh open this image this is just a 512 by 512 so it's a small image but uh you get the point now in the little node down here you have the width and the height and the batch size which is how many images you will create and in the K sampler here you have the seed which basically determines the base noise before this image is generated this can be changed and it can be set to fix an increment increasing one at a time or decrement decreasing one at a time for example the number of steps that your
6:12 image will go through while rendering and the CFG scale which is a mathematical equation between the positive prompt and the negative prompt and the output so but simply put its lower CFG means that AI is listening less to your prompt I'd say a value between three 7ish it's kind of good I usually do four or five nowadays the sampler here is basically what renders your image now for stabil Fusion 1.5 and 2.0 models I recommend the DPM Plus+ 2m and then changing the scheduler to Caris but this is basically the super simple version of com UI and the nodes now you
6:57 can add more nodes there are a lot of available so just right click some thing you can add a node and there are a lot of nodes to choose from so let's say here for example this is the cas sampler so this is some of the settings that are used to render an image if we add an advanced case sampler you can see here that they're getting some more settings we can have a start at step and an end that step which means we could run multiple Cas Samplers like one running from 0 to 15 and another from 15 to 30 this is very popular in sdx Excel where you're running the sdxl model for 25 steps and then the sdxl refiner for the last five steps but again that's a little more advanced so that's um for
7:43 another video now another fantastic feature in comy UI is that you can actually take an image so this is an image I got from a user on my Discord and if you take this and drag that straight into confy UI well first of all it's going to give us some errors but that's not the point here what you actually get is the workflow and all the nodes that we use to create this image all the settings everything and that is really powerful so you can check on other images find their workflows and um well learn from there and continue iterating you might be getting errors like I am and that's because you are missing nodes and in this example we're
8:30 missing custom nodes we're missing some uh crg sdl sdxl Samplers here and there's actually something called the comy UI manager so we're going to download this that's going to help us install custom notes so we have the zp here and this is our confy UI folder we're going to go into confy UI and then into custom nodes and then we're just going to well basically extract everything I'm just going to drag and drop that into here and after that you need to read start your confy UI so we're running this again and now you should have we're still getting the errors but don't mind that because you have the manager down here and here you can like it says install custom nodes or
9:16 install missing custom nodes so let's press the little install missing custom noes button here so this is crg sdxl we're installing that now it says to apply the install custom node please reinart cofy UI so we will do that again and as you can see now we have now gotten our new workflow here working so we just loaded another users's image and let's cue The Prompt here and see if we get a similar result you can see here that the green border here shows what node is active so it's actually rendering here now and here we have so this is exactly the same image that I got from the user on Discord so that's pretty cool eh but you get the idea of
10:04 how powerful this node-based system is so you get a lot of control and a lot of freedom and a lot of help if you can just load another user's um workflow and just remember to download that manager so you can install the required custom nodes now there are also a lot of other nodes you can check out to yourself so there's a whole list here of custom nodes available similar to the extensions tab in automatic 1111 so I'd recommend looking at the base UI try to see what node does what look at the the green border when you're generating an image and then find another image check that particular workflow and see how
10:50 other users are creating their fantastic images now if you want to learn more in depth com for UI has a lot of examples in their GitHub so for example you can see an in painting node setup right here so here's an example of how you would set up a node to in paint a picture so in the example here you can see see that image is a cat here and we have first loaded a checkpoint or model we have the positive and the negative prompt we have the sampler and we have also added a VA n code for in paint and that runs from the vae from the checkpoint here here and then runs into a load image with the pixels to the image and a mask to the
11:38 mask and then you're painting on top of the Mask here and then that encode for in paint runs back into the lat image for the case sampler here so you're basically adding on top of current workflow so this is very similar to what we saw as the default here in the video when we started another example here is Laura for example we have the usual workflow we have the the checkpoint or the model we have the positive prompt and the negative prompt and the sampler and the vad code and then they've added a separate Lura loader here so instead of going from the model straight into the K sampler it goes from the model to the Lura loader and then continues onto
12:24 the K sampler and the same goes with the clip so there are a lot of good examples you can find on the comfy UI tub so this was a quick guide to get you started with comfy UI if you want to learn more about comy UI check out this sdxl workflow and this video wres oh the side as always have a good one see you
